Update app.py

app.py

@@ -53,100 +53,6 @@ uploads_dir = os.path.join(app.root_path,'static', 'uploads')
 
 os.makedirs(uploads_dir, exist_ok=True)
 
-vectordb = createVectorDB(loadKB(False, False, uploads_dir, None))
-
-@app.route('/', methods=['GET'])
-def test():
-    return "Docker hello"
-
-@app.route('/KBUploader')
-def KBUpload():
-    return render_template("KBTrain.html")
-
-@app.route('/aiassist')
-def aiassist():
-    return render_template("index.html")
-
-@app.route('/agent/chat/suggestion', methods=['POST'])
-def process_json():
-    print(f"\n{'*' * 100}\n")
-    print("Request Received >>>>>>>>>>>>>>>>>>", datetime.now().strftime("%H:%M:%S"))
-    content_type = request.headers.get('Content-Type')
-    if (content_type == 'application/json'):
-        requestQuery = request.get_json()
-        print(type(requestQuery))
-        custDetailsPresent=False
-        customerName=""
-        customerDistrict=""
-        if("custDetails" in requestQuery):
-            custDetailsPresent = True
-            customerName=requestQuery['custDetails']['cName']
-            customerDistrict=requestQuery['custDetails']['cDistrict']
-
-        print("chain initiation")
-        chainRAG=getRAGChain(customerName, customerDistrict, custDetailsPresent,vectordb)
-        print("chain created")
-        suggestionArray = []
-
-        for index, query in enumerate(requestQuery['message']):
-            #message = answering(query)
-            relevantDoc = vectordb.similarity_search_with_score(query)
-            for doc in relevantDoc:
-                print(f"\n{'-' * 100}\n")
-                print("Document Source>>>>>>  " + doc[len(doc) - 2].metadata['source'] + "\n\n")
-                print("Page Content>>>>>> " + doc[len(doc) - 2].page_content + "\n\n")
-                print("Similarity Score>>>> " + str(doc[len(doc) - 1]))
-                print(f"\n{'-' * 100}\n")
-            message = chainRAG.run({"query": query})
-            print("query:",query)
-            print("Response:", message)
-            if "I don't know" in message:
-                 message = "Dear Sir/ Ma'am, Could you please ask questions relevant to Jio?"
-            responseJSON={"message":message,"id":index}
-            suggestionArray.append(responseJSON)
-        return jsonify(suggestions=suggestionArray)
-    else:
-        return 'Content-Type not supported!'
-
-@app.route('/file_upload', methods=['POST'])
-def file_Upload():
-    fileprovided = not request.files.getlist('files[]')[0].filename == ''
-    urlProvided = not request.form.getlist('weburl')[0] == ''
-    print("*******")
-    print("File Provided:" + str(fileprovided))
-    print("URL Provided:" + str(urlProvided))
-    print("*******")
-
-    print(uploads_dir)
-    documents = loadKB(fileprovided, urlProvided, uploads_dir, request)
-    vectordb=createVectorDB(documents)
-    return render_template("index.html")
-
-def createPrompt(cName, cCity, custDetailsPresent):
-    cProfile = "Customer's Name is " + cName + "\nCustomer's lives in or customer's Resident State or Customer's place is " + cCity + "\n"
-    print(cProfile)
-
-    template1 = """You role is of a Professional Customer Support Executive and your name is Jio AIAssist.
-        You are talking to the below customer whose information is provided in block delimited by <cp></cp>.
-        Use the following customer related information (delimited by <cp></cp>) and context (delimited by <ctx></ctx>) to answer the question at the end by thinking step by step alongwith reaonsing steps:
-        If you don't know the answer, just say that you don't know, don't try to make up an answer.
-        Use the customer information to replace entities in the question before answering\n
-        \n"""
-
-    template2 = """
-        <ctx>
-        {context}
-        </ctx>
-        <hs>
-        {history}
-        </hs>
-        Question: {question}
-        Answer: """
-
-    prompt_template = template1 + "<cp>\n" + cProfile + "\n</cp>\n" + template2
-    PROMPT = PromptTemplate(template=prompt_template, input_variables=["history", "context", "question"])
-    return PROMPT
-
 
 def pretty_print_docs(docs):
     print(f"\n{'-' * 100}\n".join([f"Document {i + 1}:\n\n" + "Document Length>>>" + str(
@@ -236,6 +142,99 @@ def createVectorDB(documents):
     vectordb = Chroma.from_documents(texts, embeddings)
     return vectordb
 
+def createPrompt(cName, cCity, custDetailsPresent):
+    cProfile = "Customer's Name is " + cName + "\nCustomer's lives in or customer's Resident State or Customer's place is " + cCity + "\n"
+    print(cProfile)
+
+    template1 = """You role is of a Professional Customer Support Executive and your name is Jio AIAssist.
+        You are talking to the below customer whose information is provided in block delimited by <cp></cp>.
+        Use the following customer related information (delimited by <cp></cp>) and context (delimited by <ctx></ctx>) to answer the question at the end by thinking step by step alongwith reaonsing steps:
+        If you don't know the answer, just say that you don't know, don't try to make up an answer.
+        Use the customer information to replace entities in the question before answering\n
+        \n"""
+
+    template2 = """
+        <ctx>
+        {context}
+        </ctx>
+        <hs>
+        {history}
+        </hs>
+        Question: {question}
+        Answer: """
+
+    prompt_template = template1 + "<cp>\n" + cProfile + "\n</cp>\n" + template2
+    PROMPT = PromptTemplate(template=prompt_template, input_variables=["history", "context", "question"])
+    return PROMPT
+
+vectordb = createVectorDB(loadKB(False, False, uploads_dir, None))
+
+@app.route('/', methods=['GET'])
+def test():
+    return "Docker hello"
+
+@app.route('/KBUploader')
+def KBUpload():
+    return render_template("KBTrain.html")
+
+@app.route('/aiassist')
+def aiassist():
+    return render_template("index.html")
+
+@app.route('/agent/chat/suggestion', methods=['POST'])
+def process_json():
+    print(f"\n{'*' * 100}\n")
+    print("Request Received >>>>>>>>>>>>>>>>>>", datetime.now().strftime("%H:%M:%S"))
+    content_type = request.headers.get('Content-Type')
+    if (content_type == 'application/json'):
+        requestQuery = request.get_json()
+        print(type(requestQuery))
+        custDetailsPresent=False
+        customerName=""
+        customerDistrict=""
+        if("custDetails" in requestQuery):
+            custDetailsPresent = True
+            customerName=requestQuery['custDetails']['cName']
+            customerDistrict=requestQuery['custDetails']['cDistrict']
+
+        print("chain initiation")
+        chainRAG=getRAGChain(customerName, customerDistrict, custDetailsPresent,vectordb)
+        print("chain created")
+        suggestionArray = []
+
+        for index, query in enumerate(requestQuery['message']):
+            #message = answering(query)
+            relevantDoc = vectordb.similarity_search_with_score(query)
+            for doc in relevantDoc:
+                print(f"\n{'-' * 100}\n")
+                print("Document Source>>>>>>  " + doc[len(doc) - 2].metadata['source'] + "\n\n")
+                print("Page Content>>>>>> " + doc[len(doc) - 2].page_content + "\n\n")
+                print("Similarity Score>>>> " + str(doc[len(doc) - 1]))
+                print(f"\n{'-' * 100}\n")
+            message = chainRAG.run({"query": query})
+            print("query:",query)
+            print("Response:", message)
+            if "I don't know" in message:
+                 message = "Dear Sir/ Ma'am, Could you please ask questions relevant to Jio?"
+            responseJSON={"message":message,"id":index}
+            suggestionArray.append(responseJSON)
+        return jsonify(suggestions=suggestionArray)
+    else:
+        return 'Content-Type not supported!'
+
+@app.route('/file_upload', methods=['POST'])
+def file_Upload():
+    fileprovided = not request.files.getlist('files[]')[0].filename == ''
+    urlProvided = not request.form.getlist('weburl')[0] == ''
+    print("*******")
+    print("File Provided:" + str(fileprovided))
+    print("URL Provided:" + str(urlProvided))
+    print("*******")
+
+    print(uploads_dir)
+    documents = loadKB(fileprovided, urlProvided, uploads_dir, request)
+    vectordb=createVectorDB(documents)
+    return render_template("index.html")
 
 if __name__ == '__main__':
     app.run(host='0.0.0.0',  port=int(os.environ.get('PORT', 7860)))